Veritas Integration

Veritas is SO1’s curated prompt library containing 255 validated prompts. Agents both consume prompts (for context and patterns) and produce prompt drafts (from learned patterns).

What is Veritas?

Veritas is a structured prompt library that provides:

Reusable prompt fragments for common tasks
Versioned and validated prompts
Domain-organized content
Bidirectional integration with agents

┌────────────────────────────────────────────────────────────────┐
│                        VERITAS LIBRARY                          │
├────────────────────────────────────────────────────────────────┤
│                                                                │
│   ┌─────────────┐  ┌─────────────┐  ┌─────────────┐           │
│   │    Task     │  │  Fragment   │  │    Chain    │           │
│   │   Prompts   │  │   Prompts   │  │   Prompts   │           │
│   │    (120)    │  │    (85)     │  │    (50)     │           │
│   └─────────────┘  └─────────────┘  └─────────────┘           │
│                                                                │
│   Organization: domain → purpose → version                     │
│                                                                │
└────────────────────────────────────────────────────────────────┘

Prompt Categories

Task Prompts
Fragment Prompts
Chain Prompts

Single-purpose instructions for specific tasks.Example ID: vrt-a1b2c3d4

{
  "id": "vrt-a1b2c3d4",
  "category": "task",
  "domain": "automation",
  "purpose": "n8n workflow design patterns",
  "version": "1.0.0",
  "content": "When designing n8n workflows, follow these patterns:\n1. Use webhook triggers for external events\n2. Include error handling nodes after each action\n3. Add retry logic with exponential backoff..."
}

Used by: Single agents for specific operations

Reusable snippets that can be composed into larger prompts.Example ID: vrt-e5f6g7h8

{
  "id": "vrt-e5f6g7h8",
  "category": "fragment",
  "domain": "engineering",
  "purpose": "Zod validation boilerplate",
  "version": "1.0.0",
  "content": "Always validate inputs with Zod:\n- Define schema before handler\n- Use .parse() for throwing validation\n- Use .safeParse() when you need error details\n- Export schemas for reuse"
}

Used by: Multiple agents, composed together

Multi-step prompt sequences for complex workflows.Example ID: vrt-chain001

{
  "id": "vrt-chain001",
  "category": "chain",
  "domain": "prompts",
  "purpose": "Design-implement-test workflow",
  "version": "1.0.0",
  "steps": [
    {"step": 1, "action": "Analyze requirements", "output": "spec"},
    {"step": 2, "action": "Design solution", "input": "spec", "output": "design"},
    {"step": 3, "action": "Implement code", "input": "design", "output": "code"},
    {"step": 4, "action": "Write tests", "input": "code", "output": "tests"}
  ]
}

Used by: Multi-step operations, Chain Architect

Agent Configuration

Each agent declares its Veritas integration in YAML frontmatter:

veritas:
  consumes:
    - id: "vrt-a1b2c3d4"
      purpose: "Workflow design patterns"
    - id: "vrt-e5f6g7h8"
      purpose: "Error handling best practices"
  produces:
    - category: task
      output_path: "veritas/agent-prompts/automation/"

Consuming Prompts

Agents reference prompts by their Veritas ID:

Field	Description
`id`	Unique Veritas ID (format: `vrt-xxxxxxxx`)
`purpose`	Why this agent uses this prompt

Producing Prompts

When agents discover novel patterns:

Field	Description
`category`	Type: `task`, `fragment`, or `chain`
`output_path`	Where draft prompts are saved

Prompt Flow

                    ┌─────────────────┐
                    │  VERITAS CORE   │
                    │  (255 prompts)  │
                    └────────┬────────┘
                             │
              ┌──────────────┼──────────────┐
              │              │              │
              ▼              ▼              ▼
       ┌──────────┐   ┌──────────┐   ┌──────────┐
       │ Workflow │   │  Prompt  │   │  Hono    │
       │ Architect│   │ Refiner  │   │ Backend  │
       └────┬─────┘   └────┬─────┘   └────┬─────┘
            │              │              │
            └──────────────┼──────────────┘
                           │
                           ▼
                    ┌─────────────────┐
                    │  AGENT DRAFTS   │
                    │ (pending review)│
                    └────────┬────────┘
                             │
                             ▼
                    ┌─────────────────┐
                    │  HUMAN REVIEW   │
                    │   (approve/     │
                    │    reject)      │
                    └────────┬────────┘
                             │
                             ▼
                    ┌─────────────────┐
                    │  VERITAS CORE   │
                    │   (promoted)    │
                    └─────────────────┘

Prompt ID Format

Veritas IDs follow a consistent format:

vrt-xxxxxxxx

Where:
- vrt- : Veritas prefix
- xxxxxxxx : 8-character alphanumeric identifier

Examples:

vrt-a1b2c3d4 - Workflow patterns
vrt-wh001xyz - Webhook security
vrt-chain001 - Design chain

Prompts by Domain

Automation Domain

Prompt ID	Purpose	Used By
`vrt-a1b2c3d4`	Workflow design patterns	Workflow Architect
`vrt-e5f6g7h8`	Error handling	Workflow Architect
`vrt-wh001`	Webhook patterns	Webhook Engineer
`vrt-sec001`	Webhook security	Webhook Engineer
`vrt-cron01`	Cron patterns	Schedule Optimizer
`vrt-tz01`	Timezone handling	Schedule Optimizer

Engineering Domain

Prompt ID	Purpose	Used By
`vrt-hono01`	Hono patterns	Hono Backend
`vrt-zod01`	Zod validation	Hono Backend
`vrt-next01`	Next.js patterns	Next.js Frontend
`vrt-react01`	React patterns	Next.js Frontend

Prompts Domain

Prompt ID	Purpose	Used By
`vrt-meta001`	Meta-prompts	Prompt Refiner
`vrt-clarity01`	Clarity patterns	Prompt Refiner
`vrt-chain001`	Chain patterns	Chain Architect
`vrt-flow001`	Data flow	Chain Architect
`vrt-fragment001`	Fragment patterns	Fragment Curator
`vrt-compose01`	Composition	Fragment Curator

Incident Domain

Prompt ID	Purpose	Used By
`vrt-incident01`	Playbooks	Incident Commander
`vrt-comms01`	Communications	Incident Commander
`vrt-triage01`	Triage patterns	Triage Responder
`vrt-symptoms01`	Symptom mapping	Triage Responder
`vrt-rca01`	RCA frameworks	Postmortem Analyst
`vrt-5whys01`	5 Whys technique	Postmortem Analyst

Draft Prompt Schema

Agent-produced drafts must conform to this schema:

{
  "$schema": "veritas-draft-schema.json",
  "metadata": {
    "source_agent": "workflow-architect",
    "discovered_at": "2024-01-15T10:30:00Z",
    "context": "Learned while designing retry patterns"
  },
  "prompt": {
    "category": "fragment",
    "domain": "automation",
    "purpose": "Exponential backoff configuration",
    "content": "For retry logic, use exponential backoff:\n- Initial delay: 1 second\n- Multiplier: 2x\n- Max retries: 5\n- Max delay: 60 seconds"
  },
  "status": "draft"
}

Review Process

Agent produces draft → saved to veritas/agent-prompts/
Human reviews → checks accuracy, relevance, quality
Approval → promoted to Veritas core with new ID
Rejection → feedback provided, draft deleted or revised

Validation

Veritas integration is validated during agent checks:

./scripts/validate-agents.sh

# Checks:
# ✓ veritas.consumes defined
# ✓ Prompt IDs match format (vrt-xxxxxxxx)
# ✓ veritas.produces has valid category
# ✓ output_path exists

FORGE Stages

Stage-gated execution model

Prompt Agents

Agents specialized in prompt engineering

Getting Started

Architecture

Veritas Integration

Veritas Integration

What is Veritas?

Prompt Categories

Agent Configuration

Consuming Prompts

Producing Prompts

Prompt Flow

Prompt ID Format

Prompts by Domain

Draft Prompt Schema

Review Process

Validation

FORGE Stages

Prompt Agents

Getting Started

Architecture

​Veritas Integration

​What is Veritas?

​Prompt Categories

​Agent Configuration

​Consuming Prompts

​Producing Prompts

​Prompt Flow

​Prompt ID Format

​Prompts by Domain

​Draft Prompt Schema

​Review Process

​Validation

​Related Documentation

FORGE Stages

Prompt Agents

Veritas Integration

What is Veritas?

Prompt Categories

Agent Configuration

Consuming Prompts

Producing Prompts

Prompt Flow

Prompt ID Format

Prompts by Domain

Draft Prompt Schema

Review Process

Validation

Related Documentation